Data-driven prediction of unsteady flow fields over a circular cylinder using deep learning

TL;DR

This paper develops deep learning models, including CNNs and GANs with physical constraints, to predict unsteady flow fields over a circular cylinder at various Reynolds numbers, demonstrating accurate flow predictions aligned with numerical simulations.

Contribution

It introduces physical loss functions and adversarial training into deep learning models for flow prediction, enhancing accuracy and physical consistency.

Findings

Deep learning models accurately predict flow fields at unseen Reynolds numbers.

Physical loss functions improve the physical fidelity of flow predictions.

Adversarial training helps extract flow dynamics features in an unsupervised manner.

Abstract

Unsteady flow fields over a circular cylinder are trained and predicted using four different deep learning networks: convolutional neural networks with and without consideration of conservation laws, generative adversarial networks with and without consideration of conservation laws. Flow fields at future occasions are predicted based on information of flow fields at previous occasions. Deep learning networks are trained first using flow fields at Reynolds numbers of 100, 200, 300, and 400, while flow fields at Reynolds numbers of 500 and 3000 are predicted using the trained deep learning networks. Physical loss functions are proposed to explicitly impose information of conservation of mass and momentum to deep learning networks. An adversarial training is applied to extract features of flow dynamics in an unsupervised manner. Effects of the proposed physical loss functions, adversarial training, and network sizes on the prediction accuracy are analyzed. Predicted flow fields using deep learning networks are in favorable agreement with flow fields computed by numerical simulations.